Kimi K3.1 Pro
Intelligence benchmarks
Artificial Analysis indexes - compared with the best open and proprietary models
Intelligence
46.5
AA Index
Coding
42.1
AA Index
Agentic
52.3
AA Index
Intelligence Index - Kimi K3.1 Pro vs. the field
Best open-weight models (you can run locally) and leading proprietary models for context.
Coding Index comparison
Agentic Index comparison
Benchmark data from Artificial Analysis · updated 2026-11-07.
Hosted API cost & speed
What it costs to rent this model instead of running it locally
| Metric | Value |
|---|---|
| Input (per 1M tokens) | $2.00 |
| Output (per 1M tokens) | $10.00 |
| Median speed (hosted API) | 27 tok/s |
Median across hosted providers, measured by Artificial Analysis - updated 2026-11-07. Local llama.cpp speed depends on your hardware — see the hardware pages for estimates.
Standard benchmarks
Performance across standard evaluations
| Benchmark | Score |
|---|---|
| HLE | 52.5 |
| SciCode | 60.8 |
Source: Artificial Analysis component evals - updated 2026-11-07.
Will it run on your hardware?
Pick your GPU memory - see which quantizations fit, and the cheapest card for the rest
Need an exact figure for your context length? Use the VRAM calculator.
Run it locally
Copy-paste - running in under a minute
vllm serve moonshotai/Kimi-K3.1-ProNew to this? Start with Ollama · serve to many users with vLLM.
Deep dive
Notes, sources, and the full write-up
Kimi K3.1 Pro is a 2780.1B-parameter other model from Kimi. It scores 46.5 on the Artificial Analysis Intelligence Index (coding 42.1). At Q4_K_M it needs roughly 1612 GB of VRAM, placing it in the 48 GB+ / multi-GPU hardware tier.
BenchmarksLink to this section
Artificial Analysis Intelligence Index - Kimi K3.1 Pro vs. leading closed models:
| Model | Intelligence | Coding | GPQA |
|---|---|---|---|
| Kimi K3.1 Pro | 46.5 | 42.1 | - |
| Gemini 4 Carbon | 60 | 50.4 | - |
| Claude Opus 5.5 | 59.1 | 51.7 | - |
| GPT-6 Astra | 56.9 | 49.1 | 96.1 |
| GPT-6.1 Sol | 54.6 | 46.8 | - |
| Claude Sonnet 5.5 | 54.5 | 50.5 | - |
Source: Artificial Analysis (2026-11-07).
PopularityLink to this section
Kimi K3.1 Pro has 18,432 downloads in the last month on HuggingFace and 1,532 likes.
Frequently asked
Quick answers to common questions
How much VRAM does Kimi K3.1 Pro need?
Kimi K3.1 Pro with 2780.1B parameters needs approximately 1612 GB at Q4_K_M quantization. Use our VRAM calculator for an exact estimate.
Is Kimi K3.1 Pro better than other moonshotai models?
Kimi K3.1 Pro has 2780.1B parameters with 1,048,576 context - a strong choice for general use.
What license is Kimi K3.1 Pro under?
Kimi K3.1 Pro is released under the other license, making it suitable for most commercial and personal projects.
What hardware runs Kimi K3.1 Pro well?
With 2780.1B parameters, Kimi K3.1 Pro requires adequate VRAM. High-end GPUs like the RTX 4090 (24GB), RTX 5090 (32GB), or Mac Studio with unified memory are good options. Check our hardware directory for specific recommendations.
What is the best quantization for Kimi K3.1 Pro?
Q4_K_M is the recommended sweet spot - ~98% of FP16 quality at ~27% of the size. Q5_K_M (~1974 GB) is an option if you have spare VRAM. Use our VRAM calculator to compare.
How long can Kimi K3.1 Pro's context window handle?
Kimi K3.1 Pro supports a 1,048,576-token context window - enough for very long documents, codebases, or multi-turn conversations. Real-world usable context may vary by implementation.
What models compete with Kimi K3.1 Pro?
Kimi K3.1 Pro competes with other 1390B–4170B. Browse our model directory for comparisons, benchmarks, and community reviews to find the best fit.
Nearby options
Similar models and compatible hardware by spec